Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and associated token structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Generated
    -0.17
    -La
    -0.15
    -www
    -0.15
    linkplain
    -0.15
     Cust
    -0.14
    浩
    -0.14
    ονÏĦαÏĤ
    -0.14
    tie
    -0.14
     môn
    -0.14
    ĥ
    -0.14
    POSITIVE LOGITS
     Orth
    0.15
    ipay
    0.15
    afs
    0.14
     =============================================================================↵
    0.14
     lump
    0.14
    .BASELINE
    0.14
    íݸ
    0.14
    .gs
    0.14
    гÑĢад
    0.14
    ortho
    0.13
    Act Density 0.000%

    No Known Activations